© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 16386
    Prev
    Next
    INDEX
    Explanations

    high frequency specifications, particularly related to processing power

    oai_token-act-pair · gpt-3.5-turbo

    references to clock speeds and processing power of computer components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     skelet
    -0.75
    bor
    -0.67
     ethn
    -0.67
     Salem
    -0.67
     Doct
    -0.64
     Hunts
    -0.64
    ROR
    -0.64
    lined
    -0.63
     Narc
    -0.62
    hall
    -0.61
    POSITIVE LOGITS
    GHz
    1.17
     GHz
    1.06
    MHz
    1.05
    hz
    0.91
     MHz
    0.91
     radios
    0.84
     chipset
    0.83
    atsu
    0.79
    ircraft
    0.78
    ategory
    0.75
    Activations Density 0.004%

    No Known Activations